SlideShare a Scribd company logo
SigOpt. Confidential.
Exploring the spectrum of black-box optimization
through customer engagements
Harvey Cheng
05/03
SigOpt. Confidential.
Bayesian optimization
SigOpt. Confidential.
Bayesian optimization
SigOpt. Confidential.
Black-box optimization
In the research literature
SigOpt. Confidential.
Black-box optimization
A spectrum from customer engagement
Can you solve this
problem for me?
Glass box
Set and forget;
leave us alone.
Black box
SigOpt. Confidential.
Black-box optimization
A spectrum from customer engagement
Glass box Black box
Academic
collaboration
SigOpt. Confidential.
Material science research
Our Pitt collaborators wanted to use BO to
accelerate their research.
• Started using SigOpt as is and got some OK
results.
• Complicated experimental set-up and
SigOpt was not a 1-to-1 perfect fit.
• Were uninspired and had a lot of questions.
SigOpt. Confidential.
Find the fabrication process for an optical device (e.g., glass) that exhibits desirable physical and optical
properties.
• High transmission
• Low haze
• High liquid contact angle
Material science research
SigOpt. Confidential.
Find the fabrication process for an optical device (e.g., glass) that exhibits desirable physical and optical
properties.
• High transmission
• Low haze
• High liquid contact angle
Material science research
500 nm 100 nm 100 nm
SigOpt. Confidential.
Bayesian optimization for material science
What are our collaborator’s limitations? Their preferences? Their aspirations? Their fears?
SigOpt. Confidential.
Bayesian optimization for material science
What are our collaborator’s limitations? Their preferences? Their aspirations? Their fears?
Extremely budget conscious.
SigOpt. Confidential.
Bayesian optimization for material science
What are our collaborator’s limitations? Their preferences? Their aspirations? Their fears?
Fear of exploration.
SigOpt. Confidential.
Bayesian optimization for material science
What are our collaborator’s limitations? Their preferences? Their aspirations? Their fears?
Expertise is a double-edged sword.
SigOpt. Confidential.
Efficient search for the desirable material
Modification and Adaptation of BO
The researchers want:
• To leverage their expertise.
How we can help:
• Careful consideration of the input parameter
space.
SigOpt. Confidential.
Efficient search for the desirable material
Modification and Adaptation of BO
The researchers want:
• Lab equipment has limited precision.
How we can help:
• Understand how equipment precision
demands a discrete domain.
SigOpt. Confidential.
Efficient search for the desirable material
Modification and Adaptation of BO
The researchers want:
• Multiobjective optimization, on a budget.
How we can help:
• Pose the problem as a constrained
optimization problem to identify key points
on the Pareto frontier.
SigOpt. Confidential.
Efficient search for the desirable material
SigOpt. Confidential.
Optimization platform
Some of our customers cannot reveal anything
about their problems.
• Masking the input parameter names
SigOpt. Confidential.
Optimization platform
Some of our customers cannot reveal anything
about their problems.
• Masking the input parameter names
• Misusage sometimes
SigOpt. Confidential.
Optimization platform
Some of our customers cannot reveal anything
about their problems.
• Masking the input parameter names
• Misusage sometimes
• Vastly different access patterns
SigOpt. Confidential.
Black-box optimization
A spectrum from customer engagement
Academic
collaboration
Glass box Black box
Optimization
platform
SigOpt. Confidential.
Optimization platform
True black-box optimization
What can we do in the absence of customer interaction?
• Nonstandard benchmarking of our optimizer
• Flexible design of the API
• Scalable computation workflow
SigOpt. Confidential.
Scalable computation workflow
Online/Offline computation
SigOpt. Confidential.
Scalable computation workflow
Online/Offline computation
SigOpt. Confidential.
Black-box optimization
A spectrum from customer engagement
Academic
collaboration
Glass box Black box
Professional
services
Optimization
platform
SigOpt. Confidential.
Customer engagement at scale
Lessons we learned from working with our friends in Academia.
1. Customers’ problems may not be addressed immediately by the existing service.
2. Customers have inherent preferences to what is considered as success and what is considered as
failure.
Can we apply the lessons we have learned and serve a broad array of customers?
SigOpt. Confidential.
Professional services
When a customer’s problem cannot be immediately solved by plugging in the SigOpt API, the PS team can
help them by
• Understanding the customer’s success criteria.
• Building one-off projects to better interface SigOpt API with the customers.
SigOpt. Confidential.
Adjusting to customer expectations
Customers may judge their experience very differently from how we perceive it.
SigOpt. Confidential.
Adjusting to customer expectations
Customers may judge their experience very differently from how we perceive it.
• “Want more exploiting, less exploring because there is one region where there is an optimal value.
Not interested in exploring poor areas of performance.” - customer A
• “Want to make sure the optimizer is effectively exploring the parameter space. Don’t mind if there’s a
bit of extra work being done so long as it is sufficiently explored.” - customer B
SigOpt. Confidential.
Production throttles
Adjusting to customer biases
Production throttles are hooks that we can build
into the system to empower PS.
• Adjust the optimization behavior to meet the
customer’s demand.
• No redeployment of code.
SigOpt. Confidential.
Our spectrum thus far
Collaboration - Services - Black box
We have some customers with whom we have a collaborative relationship.
For most of customers, we treat their problems as completely black box.
We have identified opportunities to allow professional services to change the black box behavior without
changing the product structure.
Is this all?
SigOpt. Confidential.
Beyond black box
2016 BayesOpt workshop: We should “Open the black-box” and go “Beyond” black-box optimization.
What are some options?
• Address problems with a different goal (e.g., balancing competing objectives).
• Provide more information (level of noise for observations).
• Operate in a different workflow.
To do this, we must understand customer’s success criteria and failure modes.
SigOpt. Confidential.
Special feature for neural networks
Beyond black box
We wanted to build a feature to effectively address neural network developers. We needed to identify the
appropriate part of the black box spectrum on which this feature should lie.
Academic
collaboration
Glass box Black box
Professional
services
Optimization
platform
SigOpt. Confidential.
Special feature for neural networks
Beyond black box
Option 1: Hyperband
• Some customers had mentioned Hyperband, which could be implemented using a Bayesian
optimization strategy in the background.
SigOpt. Confidential.
Special feature for neural networks
Beyond black box
Option 1: Hyperband
• Some customers had mentioned Hyperband, which could be implemented using a Bayesian
optimization strategy in the background.
Complication:
• When confronted with the required change in workflow (storing weights, work split across generations,
idle machines), and the prospect of stopping SGD before convergence, customers balked.
Conclusion:
• Workflow change was too much towards glass box.
SigOpt. Confidential.
Special feature for neural networks
Beyond black box
Option 2: Multi-task BO
• We have a multi-task BO feature already in place; maybe neural network customers could be
convinced to use that.
SigOpt. Confidential.
Special feature for neural networks
Beyond black box
Option 2: Multi-task BO
• We have a multi-task BO feature already in place; maybe neural network customers could be
convinced to use that.
Complication:
• During customer interviews, we found customers confused by the definition of tasks and how to define
them effectively. They also disliked stopping SGD runs before convergence.
Conclusion:
• Existing multi-task feature was too black box.
SigOpt. Confidential.
Special feature for neural networks
Beyond black box
Resolution: Training Monitor
• Respect the customer’s workflow (no change required).
• Customers report progress during training.
• Allow customers to monitor training and provide status updates regarding convergence.
• Better internal models are built from all the progress information.
Conclusion:
• Does this fall in the best location of the spectrum?
SigOpt. Confidential.
Black-box optimization
A spectrum from customer engagement
Academic
collaboration
Glass box Black box
Professional
services
Optimization
platform
HPO for neural
networks
SigOpt. Confidential.
Thank You
Paul Leu
Sajad Haghanifar
@University of Pittsburgh
The entire SigOpt team.
Special thanks to our gracious hosts, Jake, Matthias, and Uber.
Hope to see you next month at ICML & CVPR! SigOpt events are being planned ...
SigOpt. Confidential.
Questions

More Related Content

Similar to SigOpt at Uber Science Symposium - Exploring the spectrum of black-box optimization through customer engagements

Product Idea Validation - 3 Factors to Consider
Product Idea Validation - 3 Factors to ConsiderProduct Idea Validation - 3 Factors to Consider
Product Idea Validation - 3 Factors to Consider
Raahul Raghavan
 
Advanced Optimization for the Enterprise Webinar
Advanced Optimization for the Enterprise WebinarAdvanced Optimization for the Enterprise Webinar
Advanced Optimization for the Enterprise Webinar
SigOpt
 
Moving away from legacy code with BDD
Moving away from legacy code with BDDMoving away from legacy code with BDD
Moving away from legacy code with BDD
Konstantin Kudryashov
 
One day Course On Agile
One day Course On AgileOne day Course On Agile
One day Course On Agile
James Whitehead
 
Usability Testing To Prioritize Your Designs
Usability Testing To Prioritize Your DesignsUsability Testing To Prioritize Your Designs
Usability Testing To Prioritize Your Designs
Elizabeth Snowdon
 
How to Build Your Product Manager Toolbox by former Microsoft PM
How to Build Your Product Manager Toolbox by former Microsoft PMHow to Build Your Product Manager Toolbox by former Microsoft PM
How to Build Your Product Manager Toolbox by former Microsoft PM
Product School
 
Bimbo Final Project Presentation
Bimbo Final Project PresentationBimbo Final Project Presentation
Bimbo Final Project PresentationCan Köklü
 
Utilizing Marginal Net Utility for Recommendation in E-commerce
Utilizing Marginal Net Utility for Recommendation in E-commerceUtilizing Marginal Net Utility for Recommendation in E-commerce
Utilizing Marginal Net Utility for Recommendation in E-commerce
Liangjie Hong
 
Research and Discovery Tools for Experimentation - 17 Apr 2024 - v 2.3 (1).pdf
Research and Discovery Tools for Experimentation - 17 Apr 2024 - v 2.3 (1).pdfResearch and Discovery Tools for Experimentation - 17 Apr 2024 - v 2.3 (1).pdf
Research and Discovery Tools for Experimentation - 17 Apr 2024 - v 2.3 (1).pdf
VWO
 
Moving away from legacy code with BDD
Moving away from legacy code with BDDMoving away from legacy code with BDD
Moving away from legacy code with BDD
Konstantin Kudryashov
 
Scrum Bangalore 13th meet up 13 june 2015 - behaviour driven development - vi...
Scrum Bangalore 13th meet up 13 june 2015 - behaviour driven development - vi...Scrum Bangalore 13th meet up 13 june 2015 - behaviour driven development - vi...
Scrum Bangalore 13th meet up 13 june 2015 - behaviour driven development - vi...
Scrum Bangalore
 
How we integrate Machine Learning Algorithms into our IT Platform at Outfitte...
How we integrate Machine Learning Algorithms into our IT Platform at Outfitte...How we integrate Machine Learning Algorithms into our IT Platform at Outfitte...
How we integrate Machine Learning Algorithms into our IT Platform at Outfitte...
OUTFITTERY
 
Modeling at scale in systematic trading
Modeling at scale in systematic tradingModeling at scale in systematic trading
Modeling at scale in systematic trading
SigOpt
 
Deep learning applications in e-commerce search: Dynamic talks Chicago 3/14/2019
Deep learning applications in e-commerce search: Dynamic talks Chicago 3/14/2019Deep learning applications in e-commerce search: Dynamic talks Chicago 3/14/2019
Deep learning applications in e-commerce search: Dynamic talks Chicago 3/14/2019
Grid Dynamics
 
Remote research uxpa talk
Remote research uxpa talkRemote research uxpa talk
Remote research uxpa talk
Gavin Fung
 
Is Quality Control in the Printindustry Build on Quicksand? (2009)
Is Quality Control in the Printindustry Build on Quicksand? (2009)Is Quality Control in the Printindustry Build on Quicksand? (2009)
Is Quality Control in the Printindustry Build on Quicksand? (2009)VIGCbe
 
GOTO Night: Decision Making Based on Machine Learning
GOTO Night: Decision Making Based on Machine LearningGOTO Night: Decision Making Based on Machine Learning
GOTO Night: Decision Making Based on Machine Learning
OUTFITTERY
 
Андрій Просов “Fixed Price Agile Projects: Lessons Learned” Kyiv Project Man...
Андрій Просов  “Fixed Price Agile Projects: Lessons Learned” Kyiv Project Man...Андрій Просов  “Fixed Price Agile Projects: Lessons Learned” Kyiv Project Man...
Андрій Просов “Fixed Price Agile Projects: Lessons Learned” Kyiv Project Man...
Lviv Startup Club
 
Portfolio_LibaiZhuo
Portfolio_LibaiZhuoPortfolio_LibaiZhuo
Portfolio_LibaiZhuoLibai Zhuo
 
BSSML17 - Introduction, Models, Evaluations
BSSML17 - Introduction, Models, EvaluationsBSSML17 - Introduction, Models, Evaluations
BSSML17 - Introduction, Models, Evaluations
BigML, Inc
 

Similar to SigOpt at Uber Science Symposium - Exploring the spectrum of black-box optimization through customer engagements (20)

Product Idea Validation - 3 Factors to Consider
Product Idea Validation - 3 Factors to ConsiderProduct Idea Validation - 3 Factors to Consider
Product Idea Validation - 3 Factors to Consider
 
Advanced Optimization for the Enterprise Webinar
Advanced Optimization for the Enterprise WebinarAdvanced Optimization for the Enterprise Webinar
Advanced Optimization for the Enterprise Webinar
 
Moving away from legacy code with BDD
Moving away from legacy code with BDDMoving away from legacy code with BDD
Moving away from legacy code with BDD
 
One day Course On Agile
One day Course On AgileOne day Course On Agile
One day Course On Agile
 
Usability Testing To Prioritize Your Designs
Usability Testing To Prioritize Your DesignsUsability Testing To Prioritize Your Designs
Usability Testing To Prioritize Your Designs
 
How to Build Your Product Manager Toolbox by former Microsoft PM
How to Build Your Product Manager Toolbox by former Microsoft PMHow to Build Your Product Manager Toolbox by former Microsoft PM
How to Build Your Product Manager Toolbox by former Microsoft PM
 
Bimbo Final Project Presentation
Bimbo Final Project PresentationBimbo Final Project Presentation
Bimbo Final Project Presentation
 
Utilizing Marginal Net Utility for Recommendation in E-commerce
Utilizing Marginal Net Utility for Recommendation in E-commerceUtilizing Marginal Net Utility for Recommendation in E-commerce
Utilizing Marginal Net Utility for Recommendation in E-commerce
 
Research and Discovery Tools for Experimentation - 17 Apr 2024 - v 2.3 (1).pdf
Research and Discovery Tools for Experimentation - 17 Apr 2024 - v 2.3 (1).pdfResearch and Discovery Tools for Experimentation - 17 Apr 2024 - v 2.3 (1).pdf
Research and Discovery Tools for Experimentation - 17 Apr 2024 - v 2.3 (1).pdf
 
Moving away from legacy code with BDD
Moving away from legacy code with BDDMoving away from legacy code with BDD
Moving away from legacy code with BDD
 
Scrum Bangalore 13th meet up 13 june 2015 - behaviour driven development - vi...
Scrum Bangalore 13th meet up 13 june 2015 - behaviour driven development - vi...Scrum Bangalore 13th meet up 13 june 2015 - behaviour driven development - vi...
Scrum Bangalore 13th meet up 13 june 2015 - behaviour driven development - vi...
 
How we integrate Machine Learning Algorithms into our IT Platform at Outfitte...
How we integrate Machine Learning Algorithms into our IT Platform at Outfitte...How we integrate Machine Learning Algorithms into our IT Platform at Outfitte...
How we integrate Machine Learning Algorithms into our IT Platform at Outfitte...
 
Modeling at scale in systematic trading
Modeling at scale in systematic tradingModeling at scale in systematic trading
Modeling at scale in systematic trading
 
Deep learning applications in e-commerce search: Dynamic talks Chicago 3/14/2019
Deep learning applications in e-commerce search: Dynamic talks Chicago 3/14/2019Deep learning applications in e-commerce search: Dynamic talks Chicago 3/14/2019
Deep learning applications in e-commerce search: Dynamic talks Chicago 3/14/2019
 
Remote research uxpa talk
Remote research uxpa talkRemote research uxpa talk
Remote research uxpa talk
 
Is Quality Control in the Printindustry Build on Quicksand? (2009)
Is Quality Control in the Printindustry Build on Quicksand? (2009)Is Quality Control in the Printindustry Build on Quicksand? (2009)
Is Quality Control in the Printindustry Build on Quicksand? (2009)
 
GOTO Night: Decision Making Based on Machine Learning
GOTO Night: Decision Making Based on Machine LearningGOTO Night: Decision Making Based on Machine Learning
GOTO Night: Decision Making Based on Machine Learning
 
Андрій Просов “Fixed Price Agile Projects: Lessons Learned” Kyiv Project Man...
Андрій Просов  “Fixed Price Agile Projects: Lessons Learned” Kyiv Project Man...Андрій Просов  “Fixed Price Agile Projects: Lessons Learned” Kyiv Project Man...
Андрій Просов “Fixed Price Agile Projects: Lessons Learned” Kyiv Project Man...
 
Portfolio_LibaiZhuo
Portfolio_LibaiZhuoPortfolio_LibaiZhuo
Portfolio_LibaiZhuo
 
BSSML17 - Introduction, Models, Evaluations
BSSML17 - Introduction, Models, EvaluationsBSSML17 - Introduction, Models, Evaluations
BSSML17 - Introduction, Models, Evaluations
 

More from SigOpt

Optimizing BERT and Natural Language Models with SigOpt Experiment Management
Optimizing BERT and Natural Language Models with SigOpt Experiment ManagementOptimizing BERT and Natural Language Models with SigOpt Experiment Management
Optimizing BERT and Natural Language Models with SigOpt Experiment Management
SigOpt
 
Experiment Management for the Enterprise
Experiment Management for the EnterpriseExperiment Management for the Enterprise
Experiment Management for the Enterprise
SigOpt
 
Efficient NLP by Distilling BERT and Multimetric Optimization
Efficient NLP by Distilling BERT and Multimetric OptimizationEfficient NLP by Distilling BERT and Multimetric Optimization
Efficient NLP by Distilling BERT and Multimetric Optimization
SigOpt
 
Detecting COVID-19 Cases with Deep Learning
Detecting COVID-19 Cases with Deep LearningDetecting COVID-19 Cases with Deep Learning
Detecting COVID-19 Cases with Deep Learning
SigOpt
 
Metric Management: a SigOpt Applied Use Case
Metric Management: a SigOpt Applied Use CaseMetric Management: a SigOpt Applied Use Case
Metric Management: a SigOpt Applied Use Case
SigOpt
 
Tuning for Systematic Trading: Talk 3: Training, Tuning, and Metric Strategy
Tuning for Systematic Trading: Talk 3: Training, Tuning, and Metric StrategyTuning for Systematic Trading: Talk 3: Training, Tuning, and Metric Strategy
Tuning for Systematic Trading: Talk 3: Training, Tuning, and Metric Strategy
SigOpt
 
Tuning for Systematic Trading: Talk 2: Deep Learning
Tuning for Systematic Trading: Talk 2: Deep LearningTuning for Systematic Trading: Talk 2: Deep Learning
Tuning for Systematic Trading: Talk 2: Deep Learning
SigOpt
 
Tuning for Systematic Trading: Talk 1
Tuning for Systematic Trading: Talk 1Tuning for Systematic Trading: Talk 1
Tuning for Systematic Trading: Talk 1
SigOpt
 
Tuning Data Augmentation to Boost Model Performance
Tuning Data Augmentation to Boost Model PerformanceTuning Data Augmentation to Boost Model Performance
Tuning Data Augmentation to Boost Model Performance
SigOpt
 
Modeling at Scale: SigOpt at TWIMLcon 2019
Modeling at Scale: SigOpt at TWIMLcon 2019Modeling at Scale: SigOpt at TWIMLcon 2019
Modeling at Scale: SigOpt at TWIMLcon 2019
SigOpt
 
Tuning 2.0: Advanced Optimization Techniques Webinar
Tuning 2.0: Advanced Optimization Techniques WebinarTuning 2.0: Advanced Optimization Techniques Webinar
Tuning 2.0: Advanced Optimization Techniques Webinar
SigOpt
 
SigOpt at Ai4 Finance—Modeling at Scale
SigOpt at Ai4 Finance—Modeling at Scale SigOpt at Ai4 Finance—Modeling at Scale
SigOpt at Ai4 Finance—Modeling at Scale
SigOpt
 
Interactive Tradeoffs Between Competing Offline Metrics with Bayesian Optimiz...
Interactive Tradeoffs Between Competing Offline Metrics with Bayesian Optimiz...Interactive Tradeoffs Between Competing Offline Metrics with Bayesian Optimiz...
Interactive Tradeoffs Between Competing Offline Metrics with Bayesian Optimiz...
SigOpt
 
Machine Learning Infrastructure
Machine Learning InfrastructureMachine Learning Infrastructure
Machine Learning Infrastructure
SigOpt
 
SigOpt at O'Reilly - Best Practices for Scaling Modeling Platforms
SigOpt at O'Reilly - Best Practices for Scaling Modeling PlatformsSigOpt at O'Reilly - Best Practices for Scaling Modeling Platforms
SigOpt at O'Reilly - Best Practices for Scaling Modeling Platforms
SigOpt
 
SigOpt at GTC - Tuning the Untunable
SigOpt at GTC - Tuning the UntunableSigOpt at GTC - Tuning the Untunable
SigOpt at GTC - Tuning the Untunable
SigOpt
 
SigOpt at GTC - Reducing operational barriers to optimization
SigOpt at GTC - Reducing operational barriers to optimizationSigOpt at GTC - Reducing operational barriers to optimization
SigOpt at GTC - Reducing operational barriers to optimization
SigOpt
 
Lessons for an enterprise approach to modeling at scale
Lessons for an enterprise approach to modeling at scaleLessons for an enterprise approach to modeling at scale
Lessons for an enterprise approach to modeling at scale
SigOpt
 
SigOpt at MLconf - Reducing Operational Barriers to Model Training
SigOpt at MLconf - Reducing Operational Barriers to Model TrainingSigOpt at MLconf - Reducing Operational Barriers to Model Training
SigOpt at MLconf - Reducing Operational Barriers to Model Training
SigOpt
 
Machine Learning Infrastructure
Machine Learning InfrastructureMachine Learning Infrastructure
Machine Learning Infrastructure
SigOpt
 

More from SigOpt (20)

Optimizing BERT and Natural Language Models with SigOpt Experiment Management
Optimizing BERT and Natural Language Models with SigOpt Experiment ManagementOptimizing BERT and Natural Language Models with SigOpt Experiment Management
Optimizing BERT and Natural Language Models with SigOpt Experiment Management
 
Experiment Management for the Enterprise
Experiment Management for the EnterpriseExperiment Management for the Enterprise
Experiment Management for the Enterprise
 
Efficient NLP by Distilling BERT and Multimetric Optimization
Efficient NLP by Distilling BERT and Multimetric OptimizationEfficient NLP by Distilling BERT and Multimetric Optimization
Efficient NLP by Distilling BERT and Multimetric Optimization
 
Detecting COVID-19 Cases with Deep Learning
Detecting COVID-19 Cases with Deep LearningDetecting COVID-19 Cases with Deep Learning
Detecting COVID-19 Cases with Deep Learning
 
Metric Management: a SigOpt Applied Use Case
Metric Management: a SigOpt Applied Use CaseMetric Management: a SigOpt Applied Use Case
Metric Management: a SigOpt Applied Use Case
 
Tuning for Systematic Trading: Talk 3: Training, Tuning, and Metric Strategy
Tuning for Systematic Trading: Talk 3: Training, Tuning, and Metric StrategyTuning for Systematic Trading: Talk 3: Training, Tuning, and Metric Strategy
Tuning for Systematic Trading: Talk 3: Training, Tuning, and Metric Strategy
 
Tuning for Systematic Trading: Talk 2: Deep Learning
Tuning for Systematic Trading: Talk 2: Deep LearningTuning for Systematic Trading: Talk 2: Deep Learning
Tuning for Systematic Trading: Talk 2: Deep Learning
 
Tuning for Systematic Trading: Talk 1
Tuning for Systematic Trading: Talk 1Tuning for Systematic Trading: Talk 1
Tuning for Systematic Trading: Talk 1
 
Tuning Data Augmentation to Boost Model Performance
Tuning Data Augmentation to Boost Model PerformanceTuning Data Augmentation to Boost Model Performance
Tuning Data Augmentation to Boost Model Performance
 
Modeling at Scale: SigOpt at TWIMLcon 2019
Modeling at Scale: SigOpt at TWIMLcon 2019Modeling at Scale: SigOpt at TWIMLcon 2019
Modeling at Scale: SigOpt at TWIMLcon 2019
 
Tuning 2.0: Advanced Optimization Techniques Webinar
Tuning 2.0: Advanced Optimization Techniques WebinarTuning 2.0: Advanced Optimization Techniques Webinar
Tuning 2.0: Advanced Optimization Techniques Webinar
 
SigOpt at Ai4 Finance—Modeling at Scale
SigOpt at Ai4 Finance—Modeling at Scale SigOpt at Ai4 Finance—Modeling at Scale
SigOpt at Ai4 Finance—Modeling at Scale
 
Interactive Tradeoffs Between Competing Offline Metrics with Bayesian Optimiz...
Interactive Tradeoffs Between Competing Offline Metrics with Bayesian Optimiz...Interactive Tradeoffs Between Competing Offline Metrics with Bayesian Optimiz...
Interactive Tradeoffs Between Competing Offline Metrics with Bayesian Optimiz...
 
Machine Learning Infrastructure
Machine Learning InfrastructureMachine Learning Infrastructure
Machine Learning Infrastructure
 
SigOpt at O'Reilly - Best Practices for Scaling Modeling Platforms
SigOpt at O'Reilly - Best Practices for Scaling Modeling PlatformsSigOpt at O'Reilly - Best Practices for Scaling Modeling Platforms
SigOpt at O'Reilly - Best Practices for Scaling Modeling Platforms
 
SigOpt at GTC - Tuning the Untunable
SigOpt at GTC - Tuning the UntunableSigOpt at GTC - Tuning the Untunable
SigOpt at GTC - Tuning the Untunable
 
SigOpt at GTC - Reducing operational barriers to optimization
SigOpt at GTC - Reducing operational barriers to optimizationSigOpt at GTC - Reducing operational barriers to optimization
SigOpt at GTC - Reducing operational barriers to optimization
 
Lessons for an enterprise approach to modeling at scale
Lessons for an enterprise approach to modeling at scaleLessons for an enterprise approach to modeling at scale
Lessons for an enterprise approach to modeling at scale
 
SigOpt at MLconf - Reducing Operational Barriers to Model Training
SigOpt at MLconf - Reducing Operational Barriers to Model TrainingSigOpt at MLconf - Reducing Operational Barriers to Model Training
SigOpt at MLconf - Reducing Operational Barriers to Model Training
 
Machine Learning Infrastructure
Machine Learning InfrastructureMachine Learning Infrastructure
Machine Learning Infrastructure
 

Recently uploaded

FIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdfFIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance
 
Neuro-symbolic is not enough, we need neuro-*semantic*
Neuro-symbolic is not enough, we need neuro-*semantic*Neuro-symbolic is not enough, we need neuro-*semantic*
Neuro-symbolic is not enough, we need neuro-*semantic*
Frank van Harmelen
 
The Future of Platform Engineering
The Future of Platform EngineeringThe Future of Platform Engineering
The Future of Platform Engineering
Jemma Hussein Allen
 
Search and Society: Reimagining Information Access for Radical Futures
Search and Society: Reimagining Information Access for Radical FuturesSearch and Society: Reimagining Information Access for Radical Futures
Search and Society: Reimagining Information Access for Radical Futures
Bhaskar Mitra
 
The Art of the Pitch: WordPress Relationships and Sales
The Art of the Pitch: WordPress Relationships and SalesThe Art of the Pitch: WordPress Relationships and Sales
The Art of the Pitch: WordPress Relationships and Sales
Laura Byrne
 
JMeter webinar - integration with InfluxDB and Grafana
JMeter webinar - integration with InfluxDB and GrafanaJMeter webinar - integration with InfluxDB and Grafana
JMeter webinar - integration with InfluxDB and Grafana
RTTS
 
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
UiPathCommunity
 
When stars align: studies in data quality, knowledge graphs, and machine lear...
When stars align: studies in data quality, knowledge graphs, and machine lear...When stars align: studies in data quality, knowledge graphs, and machine lear...
When stars align: studies in data quality, knowledge graphs, and machine lear...
Elena Simperl
 
From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...
From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...
From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...
Product School
 
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
Product School
 
De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...
De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...
De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...
Product School
 
Designing Great Products: The Power of Design and Leadership by Chief Designe...
Designing Great Products: The Power of Design and Leadership by Chief Designe...Designing Great Products: The Power of Design and Leadership by Chief Designe...
Designing Great Products: The Power of Design and Leadership by Chief Designe...
Product School
 
Unsubscribed: Combat Subscription Fatigue With a Membership Mentality by Head...
Unsubscribed: Combat Subscription Fatigue With a Membership Mentality by Head...Unsubscribed: Combat Subscription Fatigue With a Membership Mentality by Head...
Unsubscribed: Combat Subscription Fatigue With a Membership Mentality by Head...
Product School
 
How world-class product teams are winning in the AI era by CEO and Founder, P...
How world-class product teams are winning in the AI era by CEO and Founder, P...How world-class product teams are winning in the AI era by CEO and Founder, P...
How world-class product teams are winning in the AI era by CEO and Founder, P...
Product School
 
Accelerate your Kubernetes clusters with Varnish Caching
Accelerate your Kubernetes clusters with Varnish CachingAccelerate your Kubernetes clusters with Varnish Caching
Accelerate your Kubernetes clusters with Varnish Caching
Thijs Feryn
 
To Graph or Not to Graph Knowledge Graph Architectures and LLMs
To Graph or Not to Graph Knowledge Graph Architectures and LLMsTo Graph or Not to Graph Knowledge Graph Architectures and LLMs
To Graph or Not to Graph Knowledge Graph Architectures and LLMs
Paul Groth
 
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered QualitySoftware Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
Inflectra
 
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Jeffrey Haguewood
 
UiPath Test Automation using UiPath Test Suite series, part 3
UiPath Test Automation using UiPath Test Suite series, part 3UiPath Test Automation using UiPath Test Suite series, part 3
UiPath Test Automation using UiPath Test Suite series, part 3
DianaGray10
 
DevOps and Testing slides at DASA Connect
DevOps and Testing slides at DASA ConnectDevOps and Testing slides at DASA Connect
DevOps and Testing slides at DASA Connect
Kari Kakkonen
 

Recently uploaded (20)

FIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdfFIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdf
 
Neuro-symbolic is not enough, we need neuro-*semantic*
Neuro-symbolic is not enough, we need neuro-*semantic*Neuro-symbolic is not enough, we need neuro-*semantic*
Neuro-symbolic is not enough, we need neuro-*semantic*
 
The Future of Platform Engineering
The Future of Platform EngineeringThe Future of Platform Engineering
The Future of Platform Engineering
 
Search and Society: Reimagining Information Access for Radical Futures
Search and Society: Reimagining Information Access for Radical FuturesSearch and Society: Reimagining Information Access for Radical Futures
Search and Society: Reimagining Information Access for Radical Futures
 
The Art of the Pitch: WordPress Relationships and Sales
The Art of the Pitch: WordPress Relationships and SalesThe Art of the Pitch: WordPress Relationships and Sales
The Art of the Pitch: WordPress Relationships and Sales
 
JMeter webinar - integration with InfluxDB and Grafana
JMeter webinar - integration with InfluxDB and GrafanaJMeter webinar - integration with InfluxDB and Grafana
JMeter webinar - integration with InfluxDB and Grafana
 
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
 
When stars align: studies in data quality, knowledge graphs, and machine lear...
When stars align: studies in data quality, knowledge graphs, and machine lear...When stars align: studies in data quality, knowledge graphs, and machine lear...
When stars align: studies in data quality, knowledge graphs, and machine lear...
 
From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...
From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...
From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...
 
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
 
De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...
De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...
De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...
 
Designing Great Products: The Power of Design and Leadership by Chief Designe...
Designing Great Products: The Power of Design and Leadership by Chief Designe...Designing Great Products: The Power of Design and Leadership by Chief Designe...
Designing Great Products: The Power of Design and Leadership by Chief Designe...
 
Unsubscribed: Combat Subscription Fatigue With a Membership Mentality by Head...
Unsubscribed: Combat Subscription Fatigue With a Membership Mentality by Head...Unsubscribed: Combat Subscription Fatigue With a Membership Mentality by Head...
Unsubscribed: Combat Subscription Fatigue With a Membership Mentality by Head...
 
How world-class product teams are winning in the AI era by CEO and Founder, P...
How world-class product teams are winning in the AI era by CEO and Founder, P...How world-class product teams are winning in the AI era by CEO and Founder, P...
How world-class product teams are winning in the AI era by CEO and Founder, P...
 
Accelerate your Kubernetes clusters with Varnish Caching
Accelerate your Kubernetes clusters with Varnish CachingAccelerate your Kubernetes clusters with Varnish Caching
Accelerate your Kubernetes clusters with Varnish Caching
 
To Graph or Not to Graph Knowledge Graph Architectures and LLMs
To Graph or Not to Graph Knowledge Graph Architectures and LLMsTo Graph or Not to Graph Knowledge Graph Architectures and LLMs
To Graph or Not to Graph Knowledge Graph Architectures and LLMs
 
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered QualitySoftware Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
 
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
 
UiPath Test Automation using UiPath Test Suite series, part 3
UiPath Test Automation using UiPath Test Suite series, part 3UiPath Test Automation using UiPath Test Suite series, part 3
UiPath Test Automation using UiPath Test Suite series, part 3
 
DevOps and Testing slides at DASA Connect
DevOps and Testing slides at DASA ConnectDevOps and Testing slides at DASA Connect
DevOps and Testing slides at DASA Connect
 

SigOpt at Uber Science Symposium - Exploring the spectrum of black-box optimization through customer engagements

  • 1. SigOpt. Confidential. Exploring the spectrum of black-box optimization through customer engagements Harvey Cheng 05/03
  • 5. SigOpt. Confidential. Black-box optimization A spectrum from customer engagement Can you solve this problem for me? Glass box Set and forget; leave us alone. Black box
  • 6. SigOpt. Confidential. Black-box optimization A spectrum from customer engagement Glass box Black box Academic collaboration
  • 7. SigOpt. Confidential. Material science research Our Pitt collaborators wanted to use BO to accelerate their research. • Started using SigOpt as is and got some OK results. • Complicated experimental set-up and SigOpt was not a 1-to-1 perfect fit. • Were uninspired and had a lot of questions.
  • 8. SigOpt. Confidential. Find the fabrication process for an optical device (e.g., glass) that exhibits desirable physical and optical properties. • High transmission • Low haze • High liquid contact angle Material science research
  • 9. SigOpt. Confidential. Find the fabrication process for an optical device (e.g., glass) that exhibits desirable physical and optical properties. • High transmission • Low haze • High liquid contact angle Material science research 500 nm 100 nm 100 nm
  • 10. SigOpt. Confidential. Bayesian optimization for material science What are our collaborator’s limitations? Their preferences? Their aspirations? Their fears?
  • 11. SigOpt. Confidential. Bayesian optimization for material science What are our collaborator’s limitations? Their preferences? Their aspirations? Their fears? Extremely budget conscious.
  • 12. SigOpt. Confidential. Bayesian optimization for material science What are our collaborator’s limitations? Their preferences? Their aspirations? Their fears? Fear of exploration.
  • 13. SigOpt. Confidential. Bayesian optimization for material science What are our collaborator’s limitations? Their preferences? Their aspirations? Their fears? Expertise is a double-edged sword.
  • 14. SigOpt. Confidential. Efficient search for the desirable material Modification and Adaptation of BO The researchers want: • To leverage their expertise. How we can help: • Careful consideration of the input parameter space.
  • 15. SigOpt. Confidential. Efficient search for the desirable material Modification and Adaptation of BO The researchers want: • Lab equipment has limited precision. How we can help: • Understand how equipment precision demands a discrete domain.
  • 16. SigOpt. Confidential. Efficient search for the desirable material Modification and Adaptation of BO The researchers want: • Multiobjective optimization, on a budget. How we can help: • Pose the problem as a constrained optimization problem to identify key points on the Pareto frontier.
  • 17. SigOpt. Confidential. Efficient search for the desirable material
  • 18. SigOpt. Confidential. Optimization platform Some of our customers cannot reveal anything about their problems. • Masking the input parameter names
  • 19. SigOpt. Confidential. Optimization platform Some of our customers cannot reveal anything about their problems. • Masking the input parameter names • Misusage sometimes
  • 20. SigOpt. Confidential. Optimization platform Some of our customers cannot reveal anything about their problems. • Masking the input parameter names • Misusage sometimes • Vastly different access patterns
  • 21. SigOpt. Confidential. Black-box optimization A spectrum from customer engagement Academic collaboration Glass box Black box Optimization platform
  • 22. SigOpt. Confidential. Optimization platform True black-box optimization What can we do in the absence of customer interaction? • Nonstandard benchmarking of our optimizer • Flexible design of the API • Scalable computation workflow
  • 23. SigOpt. Confidential. Scalable computation workflow Online/Offline computation
  • 24. SigOpt. Confidential. Scalable computation workflow Online/Offline computation
  • 25. SigOpt. Confidential. Black-box optimization A spectrum from customer engagement Academic collaboration Glass box Black box Professional services Optimization platform
  • 26. SigOpt. Confidential. Customer engagement at scale Lessons we learned from working with our friends in Academia. 1. Customers’ problems may not be addressed immediately by the existing service. 2. Customers have inherent preferences to what is considered as success and what is considered as failure. Can we apply the lessons we have learned and serve a broad array of customers?
  • 27. SigOpt. Confidential. Professional services When a customer’s problem cannot be immediately solved by plugging in the SigOpt API, the PS team can help them by • Understanding the customer’s success criteria. • Building one-off projects to better interface SigOpt API with the customers.
  • 28. SigOpt. Confidential. Adjusting to customer expectations Customers may judge their experience very differently from how we perceive it.
  • 29. SigOpt. Confidential. Adjusting to customer expectations Customers may judge their experience very differently from how we perceive it. • “Want more exploiting, less exploring because there is one region where there is an optimal value. Not interested in exploring poor areas of performance.” - customer A • “Want to make sure the optimizer is effectively exploring the parameter space. Don’t mind if there’s a bit of extra work being done so long as it is sufficiently explored.” - customer B
  • 30. SigOpt. Confidential. Production throttles Adjusting to customer biases Production throttles are hooks that we can build into the system to empower PS. • Adjust the optimization behavior to meet the customer’s demand. • No redeployment of code.
  • 31. SigOpt. Confidential. Our spectrum thus far Collaboration - Services - Black box We have some customers with whom we have a collaborative relationship. For most of customers, we treat their problems as completely black box. We have identified opportunities to allow professional services to change the black box behavior without changing the product structure. Is this all?
  • 32. SigOpt. Confidential. Beyond black box 2016 BayesOpt workshop: We should “Open the black-box” and go “Beyond” black-box optimization. What are some options? • Address problems with a different goal (e.g., balancing competing objectives). • Provide more information (level of noise for observations). • Operate in a different workflow. To do this, we must understand customer’s success criteria and failure modes.
  • 33. SigOpt. Confidential. Special feature for neural networks Beyond black box We wanted to build a feature to effectively address neural network developers. We needed to identify the appropriate part of the black box spectrum on which this feature should lie. Academic collaboration Glass box Black box Professional services Optimization platform
  • 34. SigOpt. Confidential. Special feature for neural networks Beyond black box Option 1: Hyperband • Some customers had mentioned Hyperband, which could be implemented using a Bayesian optimization strategy in the background.
  • 35. SigOpt. Confidential. Special feature for neural networks Beyond black box Option 1: Hyperband • Some customers had mentioned Hyperband, which could be implemented using a Bayesian optimization strategy in the background. Complication: • When confronted with the required change in workflow (storing weights, work split across generations, idle machines), and the prospect of stopping SGD before convergence, customers balked. Conclusion: • Workflow change was too much towards glass box.
  • 36. SigOpt. Confidential. Special feature for neural networks Beyond black box Option 2: Multi-task BO • We have a multi-task BO feature already in place; maybe neural network customers could be convinced to use that.
  • 37. SigOpt. Confidential. Special feature for neural networks Beyond black box Option 2: Multi-task BO • We have a multi-task BO feature already in place; maybe neural network customers could be convinced to use that. Complication: • During customer interviews, we found customers confused by the definition of tasks and how to define them effectively. They also disliked stopping SGD runs before convergence. Conclusion: • Existing multi-task feature was too black box.
  • 38. SigOpt. Confidential. Special feature for neural networks Beyond black box Resolution: Training Monitor • Respect the customer’s workflow (no change required). • Customers report progress during training. • Allow customers to monitor training and provide status updates regarding convergence. • Better internal models are built from all the progress information. Conclusion: • Does this fall in the best location of the spectrum?
  • 39. SigOpt. Confidential. Black-box optimization A spectrum from customer engagement Academic collaboration Glass box Black box Professional services Optimization platform HPO for neural networks
  • 40. SigOpt. Confidential. Thank You Paul Leu Sajad Haghanifar @University of Pittsburgh The entire SigOpt team. Special thanks to our gracious hosts, Jake, Matthias, and Uber. Hope to see you next month at ICML & CVPR! SigOpt events are being planned ...